https://github.com/run-llama/llama_index/issues/17428


Hi Folks,
A brief overview of what i am trying to do:
I am making a multi-tool agent which will be having 3 different tools as of now, 2 are QueryEngineTool and 1 is FunctionTool .
I am using open source model -- microsoft/Phi-3-mini-4k-instruct model using llama_index HuggingFace and models/gemini-1.5-flash model.

HuggingFace model will be used by the tool to perfrom the given task.
Gemini -- will be used by the llama_index agent.


For faster inference and optimized memory utiluzation i am using llama_index Vllm on top of huggingface llm.

At the end i am using A CustomReAct agent toperform the given task.

Everything is working fine but the issue arrises when i am deploying it using gradio. There is a version conflict while installing gradio it is not able to find any suitable version, i tried using poetry as well but that too is not working.
I have also raised an issue of llama_index git, if anyone has worked on any such similar task please help me out with this.

I have attached a link that gives a detailed explanation about the version conflict.
Thanks for your time.

Hi Everyone, no doubt llama_index is an amazing tool to explore, but i am facing an issue.
Detailed description of what has been done
I am building a multi tool AI agent, which has 3 different tools.
2 QueryEngine Tools and one Function Tool.

I used llama_index evaluation metrics to measure my model performance, it doing good. The only issue i am facing is my agent answers the given query but is does not returns any answer, instead it get diverges from original query ending up by either hitting maximum iteration or no response.
I am attaching a SS of my agent inference, to give a clear picture of what is happening.

Please help me out with this i have tried change prompt templates, contexts of tool, engine and agent.
Tried to make a wrapper class that sets the active query to None if the agent diverges from original query but nothing is working.


Any of your help, insights would be very useful to me. Please help me out with this.
Thank You.